Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,16 @@
+# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-# Copy all files from the current directory to the container's working directory
+# Copy all files from the current directory on the host to the container's /app directory
 COPY . .
 
-# Install dependencies from the requirements file without using cache to reduce image size
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install -r requirements.txt
 
-# Define the command to start the application using Gunicorn with 4 worker processes
-# - `-w 4`: Uses 4 worker processes for handling requests
-# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
-# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
-CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:extralearn_predictor_api"]
+# Define the command to run the Streamlit app on port 8501 and make it accessible externally
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
+
+# NOTE: Disable XSRF protection for easier external access in order to make status predictions

app.py

@@ -1,85 +1,56 @@
-# Import necessary libraries
-import numpy as np
-import joblib  # For loading the serialized model
-import pandas as pd  # For data manipulation
-from flask import Flask, request, jsonify  # For creating the Flask API
-
-# Initialize the Flask application
-extralearn_predictor_api = Flask("extra Learn Status Predictor")
-
-# Load the trained machine learning model
-model = joblib.load("extralearn.joblib")
-
-# Define a route for the home page (GET request)
-@extralearn_predictor_api.get('/')
-def home():
-    """
-    This function handles GET requests to the root URL ('/') of the API.
-    It returns a simple welcome message.
-    """
-    return "Welcome to the Airbnb Rental Price Prediction API!"
-
-# Define an endpoint for single property prediction (POST request)
-@extralearn_predictor_api.post('/v1/extralearn')
-def predict_extralearn():
-    """
-    This function handles POST requests to the '/v1/extralearn' endpoint.
-    It expects a JSON payload containing property details and returns
-    the predicted rental price as a JSON response.
-    """
-    # Get the JSON data from the request body
-    extralearn_data = request.get_json()
-
-    # Extract relevant features from the JSON data
-    sample = {
-        'age': extralearn_data['age'],
-        'profile_completed': extralearn_data['profile_completed'],
-        'current_occupation': extralearn_data['current_occupation'],
-        'first_interaction': extralearn_data['first_interaction'],
-        'last_activity': extralearn_data['last_activity'],
-        'referral': extralearn_data['referral'],
-        'digital_media': extralearn_data['digital_media']
-    }
-
-    # Convert the extracted data into a Pandas DataFrame
-    input_data = pd.DataFrame([sample])
-
-    # Make prediction (get log_price)
-    predicted_status = model.predict(input_data)[0]
-
-    
-
-    # Return the actual price
-    return jsonify({'Predicted Status': predicted_status})
-
-
-# Define an endpoint for batch prediction (POST request)
-@extralearn_predictor_api.post('/v1/extralearnbatch')
-def predict_rental_price_batch():
-    """
-    This function handles POST requests to the '/v1/extralearnbatch' endpoint.
-    It expects a CSV file containing property details for multiple properties
-    and returns the predicted rental prices as a dictionary in the JSON response.
-    """
-    # Get the uploaded CSV file from the request
-    file = request.files['file']
-
-    # Read the CSV file into a Pandas DataFrame
-    input_data = pd.read_csv(file)
-
-    # Make predictions for all properties in the DataFrame (get log_prices)
-    predicted_status = model.predict(input_data).tolist()
-
-    
-
-    # Create a dictionary to store the predictions
-    output_dict = {
-        'Predicted Status': predicted_status
-    }
-
-    # Return the predictions dictionary as a JSON response
-    return output_dict
-
-# Run the Flask application in debug mode if this script is executed directly
-if __name__ == '__main__':
-    extralearn_predictor_api.run(debug=True)
+import streamlit as st
+import pandas as pd
+import requests
+
+# Set the title of the Streamlit app
+st.title("Extra Learn Status Prediction")
+
+# Section for online prediction
+st.subheader("Online Prediction")
+
+# Collect user input for property features
+age = st.number_input("age", min_value=1, value=75)
+profile_completed = st.selectbox("profile_completed", ["Yes", "No"])
+current_occupation = st.selectbox("current_occupation", ["Unemployed", "Professional", "Student"])
+last_activity =st.selectbox("last_activity", ["Yes", "No"])
+first_interaction = st.selectbox("first_interaction", ["Yes", "No"])
+referral = st.selectbox("referral", ["Yes", "No"])
+digital_media = st.selectbox("digital_media", ["Yes", "No"])
+
+# Convert user input into a DataFrame
+input_data = pd.DataFrame([{
+        'age': age,
+        'profile_completed': profile_completed,
+        'current_occupation': current_occupation,
+        'first_interaction': first_interaction,
+        'last_activity':last_activity,
+        'referral': referral,
+        'digital_media': digital_media
+}])
+
+
+# Make prediction when the "Predict" button is clicked
+if st.button("Predict"):
+    response = requests.post("https://<username>-<repo_id>.hf.space/v1/rental", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
+    if response.status_code == 200:
+        prediction = response.json()['Predicted Status']
+        st.success(f"Predicted Status: {prediction}")
+    else:
+        st.error("Error making prediction.")
+
+# Section for batch prediction
+st.subheader("Status Prediction")
+
+# Allow users to upload a CSV file for batch prediction
+uploaded_file = st.file_uploader("Upload CSV file for Status prediction", type=["csv"])
+
+# Make batch prediction when the "Predict Batch" button is clicked
+if uploaded_file is not None:
+    if st.button("Predict Status"):
+        response = requests.post("https://<username>-<repo_id>.hf.space/v1/rentalbatch", files={"file": uploaded_file})  # Send file to Flask API
+        if response.status_code == 200:
+            predictions = response.json()
+            st.success("Status predictions completed!")
+            st.write(predictions)  # Display the predictions
+        else:
+            st.error("Error making status prediction.")

requirements.txt

@@ -1,11 +1,3 @@
 pandas==2.2.2
-numpy==2.0.2
-scikit-learn==1.6.1
-xgboost==2.1.4
-joblib==1.4.2
-Werkzeug==2.2.2
-flask==2.2.2
-gunicorn==20.1.0
 requests==2.28.1
-uvicorn[standard]
 streamlit==1.43.2